You asked
Before anyone takes a turn, how is everything laid out on the table?
Answered counted as answeredAsked with: Cartographers Heroesbg-315767-en-1e
1. Give each player a blank map sheet [1]. 2. Players collectively decide whether to use the wilderness side (C) or the wastelands side (D) [1]. 3. Give each player a pencil [1]. 4. Have each player write a name for their cartographer at the top of their map sheet, optionally adding a title and family crest [1]. 5. Place the edict cards in a face-up row in the center of the play area, arranged in alphabetical order: edict A > edict B > edict C > edict D [1]. 6. Sort the scoring cards into four stacks by their card backs, shuffle each stack separately, then draw one card from each stack [1]. 7. Place one scoring card face up below each edict card, assigning them at random [1]. 8. Place the season cards in a face-up stack, arranged in order from top to bottom by the progression of the seasons: spring, summer, fall, winter [2]. 9. Shuffle the ambush cards to form a face-down deck and place this deck off to one side of the play area [2]. 10. Shuffle the hero cards to form a face-down deck and place this deck off to one side of the play area [2]. 11. Shuffle the explore cards to form a face-down deck [2]. 12. Take the top card of the ambush deck and the hero deck, then shuffle them into the explore deck without revealing them [2]. 13. Place the explore deck next to the season stack [2].
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 229 ms · ask 5945 ms · total 6183 ms
- single-flight (PR-5)
- queued 0 ms · generation 6183 ms
- retrieval refs (raw)
- [{"page": 6, "score": 0.032787, "snippet": "The game is played over four seasons . Each season is divided into multiple turns , and each turn has three phases : the Explore Phase, Draw Phase, and Check Phase. At the end of each season, players earn reputation stars. Reveal the top card of the explore deck and place it face up in the center of", "headingPath": "How to Play v · 1. EXPLORE PHASE · 2. DRAW PHASE", "sharpsignalDocId": 467}, {"page": 5, "score": 0.032258, "snippet": "Place the season cards in a face-up stack. Arrange them in order, from top to bottom, by the progression of the seasons: spring, summer, fall, winter. Shuffle the ambush cards to form a face-down deck. Place this ambush deck off to one side of the play area. Shuffle the hero cards to form a face-dow", "headingPath": "Game Setup v", "sharpsignalDocId": 467}, {"page": 11, "score": 0.031746, "snippet": "Discard the top season card from the stack and return it to the game box. This will reveal the next season card in the stack. Reshuffle the explore deck , including all explore cards revealed this season. Take the top card of the ambush deck and hero deck, then shuffle them into the explore deck, wi", "headingPath": "PREPARING FOR THE NEXT SEASON · End of the Game v · Scoring Cards v", "sharpsignalDocId": 467}, {"page": 7, "score": 0.03125, "snippet": "The chosen shape cannot overlap filled spaces or the edge of the map. Mountain spaces and wasteland spaces count as filled spaces. The chosen shape can overlap empty ruins spaces. Ruins have no effect unless Cartographers Heroes and Cartographers are combined. The chosen shape can be rotated and/or ", "headingPath": "DRAWING SHAPES · GAINING COINS", "sharpsignalDocId": 467}, {"page": 10, "score": 0.030769, "snippet": "At the end of each season, the players are evaluated. They earn reputation stars based on how well they followed the queen's edicts. Examine the current season card to see which two scoring cards to evaluate. For example, in spring, evaluate the scoring cards assigned to edicts A and B. Each player ", "headingPath": "End of the Season v · SCORING THE QUEEN'S EDICTS", "sharpsignalDocId": 467}, {"page": 9, "score": 0.030303, "snippet": "Some spaces on a player's map might get destroyed. When a space is destroyed, draw a large 'X' over the space. Destroyed spaces count as filled spaces, but have no terrain type. If a hero space is destroyed, that hero's attack pattern remains active. Check to see if the end of the season has been re", "headingPath": "DESTROYING SPACES · 3. CHECK PHASE", "sharpsignalDocId": 467}, {"page": 4, "score": 0.029851, "snippet": "Give each player a blank map sheet . Players collectively decide whether to use the wilderness side (C) or the wastelands side (D). Give each player a pencil . If playing with more than four players, additional pencils will need to be provided. Have each player write a name for their cartographer at", "headingPath": "Game Setup v", "sharpsignalDocId": 467}, {"page": 8, "score": 0.029412, "snippet": "When an ambush card is revealed, check the direction of the arrow shown on the card: clockwise or counter-clockwise. Each player immediately passes their map sheet to their neighbor in that direction. Each player draws the depicted monster shape on their neighbor's map, then fills it with the monste", "headingPath": "RESOLVING AMBUSHES · RESOLVING HEROES", "sharpsignalDocId": 467}]
- citations (raw)
- [{"page": 4, "quote": null, "headingPath": "Game Setup v", "sharpsignalDocId": 467}, {"page": 5, "quote": null, "headingPath": "Game Setup v", "sharpsignalDocId": 467}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 467 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 467 boosted
- answered-before recall
-
this ruling was answered, so past rulings were not offered
similarity threshold in force: 0.55 (rulesage.answered-before.similarity-threshold; the exact-question tier is not gated by it)
- debug row retained until
- Nov 7, 2026 05:50
retrieval — what the search arm returned
score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. This ruling ran the THREE-ARM fuse (full-text + vector + the doc-priority boost arm, which carried the base rulebook and/or the errata corrections this query matched), whose arithmetic ceiling is 0.04918 — all three arms ranking the same chunk #1 (ceiling = arms/(k+1) at k=60). The measured healthy band 0.016–0.033 was measured on TWO-arm asks and does not bound this one: its high end is the two-arm ceiling, and a third arm has room above it. A chunk only one arm ranked highly lands near 0.016 (that one arm's #1 vote), so 0.03 here is an excellent hit, not a 3% match.
per-arm ranks (the rank each search arm gave a chunk): NOT DISCLOSED by the gateway. Fusion happens gateway-side and only the FUSED score crosses the wire, so rulesage cannot show them without a gateway change. The rank column below is the FUSED rank (position in the returned list), which is real.
token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.
| fused rank | document | heading | page | fused RRF score | snippet chars |
|---|---|---|---|---|---|
| #1 | RULEBOOK Cartographers Heroes — Rulebook (corpus doc 467) | How to Play v · 1. EXPLORE PHASE · 2. DRAW PHASE | p.6 | 0.032787 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #2 | RULEBOOK Cartographers Heroes — Rulebook (corpus doc 467) | Game Setup v | p.5 | 0.032258 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #3 | RULEBOOK Cartographers Heroes — Rulebook (corpus doc 467) | PREPARING FOR THE NEXT SEASON · End of the Game v · Scoring Cards v | p.11 | 0.031746 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #4 | RULEBOOK Cartographers Heroes — Rulebook (corpus doc 467) | DRAWING SHAPES · GAINING COINS | p.7 | 0.03125 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #5 | RULEBOOK Cartographers Heroes — Rulebook (corpus doc 467) | End of the Season v · SCORING THE QUEEN'S EDICTS | p.10 | 0.030769 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #6 | RULEBOOK Cartographers Heroes — Rulebook (corpus doc 467) | DESTROYING SPACES · 3. CHECK PHASE | p.9 | 0.030303 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #7 | RULEBOOK Cartographers Heroes — Rulebook (corpus doc 467) | Game Setup v | p.4 | 0.029851 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #8 | RULEBOOK Cartographers Heroes — Rulebook (corpus doc 467) | RESOLVING AMBUSHES · RESOLVING HEROES | p.8 | 0.029412 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
chosen chunks — what the answer actually cited
token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.
| # | document | heading | page | quote chars |
|---|---|---|---|---|
| [1] | RULEBOOK Cartographers Heroes — Rulebook (corpus doc 467) | Game Setup v | p.4 | no quote on the wire |
| [2] | RULEBOOK Cartographers Heroes — Rulebook (corpus doc 467) | Game Setup v | p.5 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 229 ms · first delta 3661 ms · total 6183 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 0 ms · retrieval 229 ms · ask 5945 ms · gateway work 6183 ms · total 6183 ms
- tokens in (the prompt the answerer read)
- 2209
- tokens out (what the answerer generated)
- 340
- tok/sec
- 137.2 tok/sec — 340 output tokens in 2.478 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 19s ago)
- stream path
- streamed — the gateway pushed at least one accumulated draft
- watchdog
- first-token watchdog: 30s per arming window (rulesage.table.first-token-watchdog-seconds), re-armed once by the passages frame — so the worst case before a reader falls back to polling is 60s. Whether it actually fired is a BROWSER-side decision that never reaches the server, so it is not recorded here. The stream path above is the server's half of that story: whether a delta was emitted at all.
- num_ctx · think posture
- both are the CHILD's settings, not rulesage's, and no ask reply carries them — an answer never states which context window or think posture produced it. The live-seat line above reads them from the running child instead, where the gateway can answer for itself; it describes the child NOW, not this ask.
disposition
- outcome
- ANSWERED — Answered
- abstain rationale (n/a — this ruling answered)
- answered — no abstain rationale applies
setup-shape — why the checklist band did or didn't render
- decision
- NOT_SETUP_SHAPED — no setup-shape pattern matched this question
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 397), so "no registered errata card matched" above could never have matched one
Errata scope: the gate above matched this ruling's own edition only. When an ask also reads an expansion, that expansion's own registered errata cards stay outside the match — a stated phase-1 limitation, not a failed lookup.